A neural-network-fusion architecture for automatic extraction of oceanographic features from satellite remote sensing imagery

Abstract

This report describes an approach for automatic feature detection from fusion of remote sensing imagery using a combination of neural network architecture and the Dempster-Shafer (DS) theory of

evidence. Deterministic or idealized shapes are used to characterize surface signatures of oceanic and atmospheric fronts manifested in satellite remote sensing imagery. Raw satellite images are processed by a bank of radial basis function (RBF) neural networks trained on idealized shapes. The final classification results from the fusion of the outputs of the separate RBF. The fusion mechanism is based on DS evidential reasoning theory. The approach is initially tested for detecting different features on a single sensor and extended to classifying features observed by multiple sensors.